Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1471
    Prev
    Next
    INDEX
    Explanations

    terms related to financial regulations and activities, particularly those concerning sanctions and anti-money laundering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Financial institutions or regulations

    np_acts-logits-general · gemini-2.0-flash

    settlement fund, treasury secretary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     typelib
    -0.75
    ContentAsync
    -0.74
     Voiture
    -0.69
     BoxFit
    -0.62
    Попис
    -0.61
    TagMode
    -0.59
     AssemblyVersion
    -0.58
    anyahu
    -0.58
     ويكيپيديا
    -0.57
     Orthop
    -0.56
    POSITIVE LOGITS
     banking
    0.81
     Banking
    0.75
     bankers
    0.69
     banker
    0.66
     Bankers
    0.66
     banks
    0.65
    Banking
    0.65
    banking
    0.64
    banks
    0.62
     SWIFT
    0.62
    Activations Density 0.125%

    No Known Activations